Skip to main content
Glama

Create, replace or delete preset

manage_preset
DestructiveIdempotent

Create, replace, or delete GenieACS presets that apply configurations to devices matching a precondition at their next inform. Confirm matching devices before overwriting a fleet-wide rule.

Instructions

Create, replace or delete a GenieACS preset. A preset is a fleet-wide rule: at their next inform, every device matching its precondition gets its configurations applied, so a broad precondition (or an empty one) reconfigures the whole fleet. Confirm the precondition and the devices it matches (search_devices with the same filter) before a put. action="put" creates or overwrites the preset with body; action="delete" removes it. body is a JSON object: weight (integer, higher wins), precondition (a MongoDB-style filter as a JSON string, e.g. "{"_tags":"office"}"), and configurations (an array of {type: "value" | "provision" | "add_object" | "delete_object", ...}). Example body: {"weight":0,"precondition":"{"_tags":"pilot"}","configurations":[{"type":"provision","name":"myScript"}]}. Read genieacs://presets/list first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>",
      "name": "<name>"
    },
    "name": "manage_preset"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoFor action="put": the preset document as a JSON object string, with weight, precondition and configurations. Ignored for "delete".
nameYesThe preset name, its id on GenieACS. It cannot contain a dot.
actionYes"put" creates or replaces the preset, "delete" removes it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.4.1
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / action / description
      Previous value: -"The operation to perform: \"put\" to create or update a preset, \"delete\" to remove it."New value: +"\"put\" creates or replaces the preset, \"delete\" removes it."
    • addedInput schema / properties / action / enum
      Added value: +[
      +  "put",
      +  "delete"
      +]
    • changedInput schema / properties / body / description
      Previous value: -"The full JSON preset document (required for action=\"put\", ignored for \"delete\"). Must contain weight, precondition, and configurations fields."New value: +"For action=\"put\": the preset document as a JSON object string, with weight, precondition and configurations. Ignored for \"delete\"."
    • changedInput schema / properties / name / description
      Previous value: -"The preset name (used as the identifier in the URL). Cannot contain dots."New value: +"The preset name, its id on GenieACS. It cannot contain a dot."
    • addedInput schema / properties / name / minLength
      Added value: +1
    • addedInput schema / properties / name / pattern
      Added value: +"^[^.]+$"
  2. Addedv0.3.3

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true; the description earns credit by explaining the actual blast radius (every matching device gets reconfigured at next inform) and that put overwrites existing presets. It does not cover auth/permission requirements or error behavior, so it stops short of the top mark.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The risk warning and the read-first instruction are front-loaded, and every sentence carries operational content with no filler. It is a dense unbroken block, though, and the example body plus the field enumeration could be tightened slightly for easier scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive fleet-wide mutation with no output schema, the description supplies the object model, both action semantics, the full body contract with example, and the verification step beforehand. Nothing an agent needs in order to call it safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, yet the description goes well beyond it: it enumerates the body fields (weight, precondition, configurations), specifies precondition is a MongoDB-style filter encoded as a JSON string, lists the four configuration types, and supplies a full example body. That resolves the main ambiguity the flat string schema leaves open.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb triad and resource ("Create, replace or delete a GenieACS preset") and immediately defines what a preset is, so the agent knows the object model, not just the operation. The two action values are explicitly mapped to their effects, distinguishing this from siblings like manage_provision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete pre-call workflow: read genieacs://presets/list first, and confirm the precondition's device match via search_devices with the same filter before a put. It also states the risk condition (broad or empty precondition reconfigures the whole fleet), which tells the agent when extra caution is required rather than leaving that to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.